Cascade analysis for intestinal contraction detection

• US 8,441,530 B2
• Filed: 03/13/2007
• Issued: 05/14/2013
• Est. Priority Date: 03/13/2006
• Status: Active Grant

• Current Assignee: Given Imaging Limited (Medtronic Plc)
• Original Assignee: Given Imaging Limited (Medtronic Plc)
• Inventors: Radeva, Petia, Vitria, Jordi, Vilarino, Fernando, Spyridonos, Panagiota, Azpiroz, Fernando, Malagelada, Juan, De Iorio, Fosca, Accarino, Anna
• Primary Examiner(s): WASEL, MOHAMED A
• Application Number:
  US12/282,700
• Publication Number:
  US 20090284589A1
• Time in Patent Office: 2,254 Days
• Field of Search: 348/61, 348/65, 348/77
• US Class Current: 348/77
• CPC Class Codes: G06F 2218/12 Classification; Matching
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/10068 Endoscopic image
• CPC Class Codes: G06T 2207/30028 Colon; Small intestine
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06T 7/136 involving thresholding

Abstract

A method and system for detection of intestinal contraction may include detecting an obstructed portion of an image frame captured in-vivo. The obstructed portion of the image frame may include an area within an image frame that is obstructed by turbid intestinal content. The method and system may set a threshold for the area of the obstructed portion in the image frame, to determine an invalid frame and may remove the invalid frame from an image stream.

Claims

1. A method to extract portions of an image stream comprising:

detecting an obstructed portion of an image frame, wherein the obstructed portion includes an area within the image frame that is obstructed by turbid intestinal content;

setting a threshold for the area of the obstructed portion in the image frame, to determine an invalid frame; and

removing the invalid frame from the image stream.

2. The method of claim 1 wherein an obstructed frame is a frame with turbid content or a wall frame or a tunnel frame.

3. The method of claim 1 wherein the invalid frame is automatically removed from the image stream.

4. The method of claim 1 wherein detecting the obstructed portion of the image frame is performed by detecting textural descriptors.

5. The method of claim 4 wherein the textural descriptors include a texture pattern consisting of bubbles.

6. The method of claim 1 wherein Gabor filters are used for detecting the obstructed portion of the image frame.

7. The method of claim 1 wherein detecting the obstructed portion of the image frame is based on color information of a given image stream.

8. A system for detection of obstructed in vivo image data comprising:

an imaging device for capturing an in vivo image stream comprising a plurality of image frames of a body lumen;

a turbid media detector to detect an obstructed portion of an image frame, wherein the obstructed portion includes an area within the image frame that is obstructed by turbid intestinal content.

9. The system of claim 8 wherein the turbid media detector is self-trained to detect intestinal juices, bubbles and content.

10. The system of claim 9 wherein the turbid media detector is trained based on color information of a given stream of images.

11. The system of claim 8 further comprising a dynamic event detector to detect a pattern of global intensity of image frames in an image frame sequence of a predefined length.

12. The system of claim 8 further comprising a wall detector to automatically detect frames in which the in-viva imaging device obtains images of a lumen wall.

13. The system of claim 8 further comprising a tunnel detector to automatically detect frames in which the lumen appears static.

14. The system of claim 8 further comprising a contraction detector to automatically detect image frames captured during contractile activity.

15. The system of claim 8 wherein the in vivo imaging device is a swallowable capsule.